feat(friendli): add Friendli provider with GLM-5.2 support (#721)

* feat(friendli): add provider + 4 models

Friendli OpenAI-compatible provider. Models: GLM-5.2, GLM-5.1,
DeepSeek-V3.2, MiniMax-M2.5. Pricing from friendli.ai pricing API.

Mirror fireworks provider pattern (commit 4a9222b):
- types: model info, schema, secret key, provider name
- api: BaseOpenAiCompatibleProvider handler at api.friendli.ai/serverless/v1
- webview: provider UI, model picker, validation, i18n (18 locales)
- tests: handler spec, ProfileValidator entry

Reasoning streams back via base handler's reasoning_content extraction.
Friendli defaults parse_reasoning=true for GLM reasoning models.

* docs(friendli): add docstrings to handler and UI component + revert bug_report.yml Friendli entry

* docs(friendli): add docstrings to handler class and settings component

* test(friendli): add wiring coverage for validate, useSelectedModel, Friendli.tsx

* test(friendli): cover onInput, ApiOptions wiring, buildApiHandler switch

* test: add friendli to SettingsView change-detection mock provider list

* test(friendli): assert supportsMaxTokens/cacheWritesPrice, cover GLM-5.1 clamping path

- Add supportsMaxTokens and cacheWritesPrice assertions to GLM-5.2
  single test and it.each model table
- Add getModelMaxOutputTokens integration tests verifying:
  - GLM-5.2: 131k < 20% of 1M context → clamp no-op
  - GLM-5.1: 131k > 20% of 200k context → clamp binds to 40k
  - GLM-5.1 with user modelMaxTokens: honors override capped at model maxTokens
- Cast friendliModels[modelId] to ModelInfo to avoid union-type
  narrowing issue with as const satisfies

* test: restrict webview-ui workers in CI to prevent JSDOM CPU starvation

---------

Co-authored-by: siyoon <leesiyoon0120@gmail.com>
Co-authored-by: Elliott de Launay <edelaunay@wealthsimple.com>

Author: 3 people

packages/types/src/global-settings.ts

@@ -316,6 +316,7 @@ export const SECRET_STATE_KEYS = [
 	"sambaNovaApiKey",
 	"zaiApiKey",
 	"fireworksApiKey",
+	"friendliApiKey",
 	"vercelAiGatewayApiKey",
 	"opencodeGoApiKey",
 	"basetenApiKey",

packages/types/src/provider-settings.ts

@@ -8,6 +8,7 @@ import {
 	bedrockModels,
 	deepSeekModels,
 	fireworksModels,
+	friendliModels,
 	geminiModels,
 	mistralModels,
 	moonshotModels,
@@ -119,6 +120,7 @@ export const providerNames = [
 	"baseten",
 	"deepseek",
 	"fireworks",
+	"friendli",
 	"gemini",
 	"gemini-cli",
 	"mistral",
@@ -393,6 +395,10 @@ const fireworksSchema = apiModelIdProviderModelSchema.extend({
 	fireworksApiKey: z.string().optional(),
 })
 
+const friendliSchema = apiModelIdProviderModelSchema.extend({
+	friendliApiKey: z.string().optional(),
+})
+
 const qwenCodeSchema = apiModelIdProviderModelSchema.extend({
 	qwenCodeOauthPath: z.string().optional(),
 })
@@ -449,6 +455,7 @@ export const providerSettingsSchemaDiscriminated = z.discriminatedUnion("apiProv
 	sambaNovaSchema.merge(z.object({ apiProvider: z.literal("sambanova") })),
 	zaiSchema.merge(z.object({ apiProvider: z.literal("zai") })),
 	fireworksSchema.merge(z.object({ apiProvider: z.literal("fireworks") })),
+	friendliSchema.merge(z.object({ apiProvider: z.literal("friendli") })),
 	qwenCodeSchema.merge(z.object({ apiProvider: z.literal("qwen-code") })),
 	vercelAiGatewaySchema.merge(z.object({ apiProvider: z.literal("vercel-ai-gateway") })),
 	opencodeGoSchema.merge(z.object({ apiProvider: z.literal("opencode-go") })),
@@ -485,6 +492,7 @@ export const providerSettingsSchema = z.object({
 	...sambaNovaSchema.shape,
 	...zaiSchema.shape,
 	...fireworksSchema.shape,
+	...friendliSchema.shape,
 	...qwenCodeSchema.shape,
 	...vercelAiGatewaySchema.shape,
 	...opencodeGoSchema.shape,
@@ -565,6 +573,7 @@ export const modelIdKeysByProvider: Record<TypicalProvider, ModelIdKey> = {
 	sambanova: "apiModelId",
 	zai: "apiModelId",
 	fireworks: "apiModelId",
+	friendli: "apiModelId",
 	"vercel-ai-gateway": "vercelAiGatewayModelId",
 	"opencode-go": "opencodeGoModelId",
 	"zoo-gateway": "zooGatewayModelId",
@@ -638,6 +647,11 @@ export const MODELS_BY_PROVIDER: Record<
 		label: "Fireworks",
 		models: Object.keys(fireworksModels),
 	},
+	friendli: {
+		id: "friendli",
+		label: "Friendli",
+		models: Object.keys(friendliModels),
+	},
 	gemini: {
 		id: "gemini",
 		label: "Google Gemini",

packages/types/src/providers/friendli.ts

@@ -0,0 +1,63 @@
+import type { ModelInfo } from "../model.js"
+
+export type FriendliModelId =
+	| "zai-org/GLM-5.2"
+	| "zai-org/GLM-5.1"
+	| "deepseek-ai/DeepSeek-V3.2"
+	| "MiniMaxAI/MiniMax-M2.5"
+
+export const friendliDefaultModelId: FriendliModelId = "zai-org/GLM-5.2"
+
+// Pricing sourced from https://friendli.ai/api/public/model-apis (per 1M tokens).
+export const friendliModels = {
+	"zai-org/GLM-5.2": {
+		maxTokens: 131_072,
+		contextWindow: 1_000_000,
+		supportsImages: false,
+		supportsPromptCache: true,
+		supportsMaxTokens: true,
+		inputPrice: 1.4,
+		outputPrice: 4.4,
+		cacheWritesPrice: 0,
+		cacheReadsPrice: 0.26,
+		description:
+			"GLM-5.2 is Zhipu's flagship model with a 1M context window and 128k max output, served via Friendli Model APIs. It delivers top-tier long-context reasoning, coding, and agentic performance for extended engineering sessions.",
+	},
+	"zai-org/GLM-5.1": {
+		maxTokens: 131_072,
+		contextWindow: 200_000,
+		supportsImages: false,
+		supportsPromptCache: true,
+		supportsMaxTokens: true,
+		inputPrice: 1.4,
+		outputPrice: 4.4,
+		cacheWritesPrice: 0,
+		cacheReadsPrice: 0.26,
+		description:
+			"GLM-5.1 is Zhipu's most capable model with a 200k context window and 128k max output, served via Friendli Model APIs. It delivers top-tier reasoning, coding, and agentic performance.",
+	},
+	"deepseek-ai/DeepSeek-V3.2": {
+		maxTokens: 16384,
+		contextWindow: 163_840,
+		supportsImages: false,
+		supportsPromptCache: true,
+		inputPrice: 0.5,
+		outputPrice: 1.5,
+		cacheWritesPrice: 0,
+		cacheReadsPrice: 0.25,
+		description:
+			"DeepSeek V3.2 is the latest iteration of the V3 model family with enhanced reasoning capabilities, improved code generation, and better instruction following, served via Friendli Model APIs.",
+	},
+	"MiniMaxAI/MiniMax-M2.5": {
+		maxTokens: 4096,
+		contextWindow: 204_800,
+		supportsImages: false,
+		supportsPromptCache: true,
+		inputPrice: 0.3,
+		outputPrice: 1.2,
+		cacheWritesPrice: 0,
+		cacheReadsPrice: 0.06,
+		description:
+			"MiniMax M2.5 is a high-performance language model with a 204.8K context window, optimized for long-context understanding and generation tasks, served via Friendli Model APIs.",
+	},
+} as const satisfies Record<string, ModelInfo>

packages/types/src/providers/index.ts

@@ -3,6 +3,7 @@ export * from "./baseten.js"
 export * from "./bedrock.js"
 export * from "./deepseek.js"
 export * from "./fireworks.js"
+export * from "./friendli.js"
 export * from "./gemini.js"
 export * from "./lite-llm.js"
 export * from "./lm-studio.js"
@@ -33,6 +34,7 @@ import { basetenDefaultModelId } from "./baseten.js"
 import { bedrockDefaultModelId } from "./bedrock.js"
 import { deepSeekDefaultModelId } from "./deepseek.js"
 import { fireworksDefaultModelId } from "./fireworks.js"
+import { friendliDefaultModelId } from "./friendli.js"
 import { geminiDefaultModelId } from "./gemini.js"
 import { litellmDefaultModelId } from "./lite-llm.js"
 import { mistralDefaultModelId } from "./mistral.js"
@@ -111,6 +113,8 @@ export function getProviderDefaultModelId(
 			return sambaNovaDefaultModelId
 		case "fireworks":
 			return fireworksDefaultModelId
+		case "friendli":
+			return friendliDefaultModelId
 		case "qwen-code":
 			return qwenCodeDefaultModelId
 		case "poe":

src/api/index.ts

@@ -31,6 +31,7 @@ import {
 	SambaNovaHandler,
 	ZAiHandler,
 	FireworksHandler,
+	FriendliHandler,
 	VercelAiGatewayHandler,
 	OpencodeGoHandler,
 	ZooGatewayHandler,
@@ -189,6 +190,8 @@ export function buildApiHandler(configuration: ProviderSettings): ApiHandler {
 			return new ZAiHandler(options)
 		case "fireworks":
 			return new FireworksHandler(options)
+		case "friendli":
+			return new FriendliHandler(options)
 		case "vercel-ai-gateway":
 			return new VercelAiGatewayHandler(options)
 		case "opencode-go":